> ## Documentation Index > Fetch the complete documentation index at: https://docs.praison.ai/llms.txt > Use this file to discover all available pages before exploring further. # Agent Train > Active iterative training with human or LLM feedback to improve agent behavior Agent Train enables active improvement of agent behavior through iterative feedback loops. Unlike [Agent Learn](/docs/concepts/agent-learn) which captures patterns passively, training uses explicit human or LLM feedback to refine responses. ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} graph TB subgraph "Agent Training Flow" I[📋 Scenario] --> A[🤖 Agent] A --> O[📝 Output] O --> G{Grader} G -->|Score + Feedback| R[🔄 Improve] R --> A end subgraph "Grading Modes" H[👤 Human Feedback] L[🧠 LLM-as-Judge] end G --> H G --> L classDef input fill:#6366F1,stroke:#7C90A0,color:#fff classDef process fill:#F59E0B,stroke:#7C90A0,color:#fff classDef output fill:#10B981,stroke:#7C90A0,color:#fff class I input class A,O,G,R process class H,L output ``` ## Quick Start Train an agent with a single input: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train agents --input "What is Python?" ``` Get human feedback instead of automated grading: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train agents --input "Explain machine learning" --human ``` Run multiple training iterations: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train agents --input "Write a poem" --iterations 5 ``` *** ## How It Works ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} sequenceDiagram participant User participant AgentTrainer participant Agent participant Grader participant Storage User->>AgentTrainer: Add scenario AgentTrainer->>Agent: Run with input Agent->>AgentTrainer: Output response AgentTrainer->>Grader: Grade output Grader->>AgentTrainer: Score + feedback AgentTrainer->>AgentTrainer: Build improvement prompt AgentTrainer->>Agent: Run improved (iteration 2) AgentTrainer->>Storage: Save training report AgentTrainer->>User: Final report ``` ### Detailed Control Flow ```mermaid theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} sequenceDiagram participant User participant AgentTrainer participant TrainingStorage participant TrainingGrader User->>AgentTrainer: praisonai train agents --input "Hello" AgentTrainer->>TrainingStorage: add_scenario() loop For each iteration AgentTrainer->>AgentTrainer: _get_agent_output(prompt) alt LLM Mode (default) AgentTrainer->>TrainingGrader: grade(input, output) TrainingGrader-->>AgentTrainer: GradeResult (score, feedback) else Human Mode (--human) AgentTrainer->>User: Print output, ask for score User-->>AgentTrainer: Score + feedback end AgentTrainer->>TrainingStorage: save_iteration() AgentTrainer->>AgentTrainer: _build_improvement_prompt end AgentTrainer->>TrainingStorage: save_report() AgentTrainer-->>User: TrainingReport ``` | Phase | Description | | ------------ | ----------------------------------- | | **Scenario** | Define input and expected output | | **Execute** | Run agent and capture response | | **Grade** | Score output (human or LLM) | | **Improve** | Build enhanced prompt from feedback | | **Iterate** | Repeat for N iterations | | **Report** | Generate training summary | *** ## SDK Usage ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonai.train.agents import AgentTrainer, TrainingScenario from praisonaiagents import Agent # Create agent agent = Agent( name="Assistant", instructions="You are a helpful assistant" ) # Create trainer trainer = AgentTrainer( agent=agent, iterations=3, human_mode=False # Use LLM grading ) # Add training scenario trainer.add_scenario(TrainingScenario( id="greeting", input_text="Hello, how are you?", expected_output="A friendly greeting response" )) # Run training report = trainer.run() print(f"Final score: {report.avg_score}/10") print(f"Improvement: {report.improvement:+.1f}") ``` *** ## Applying Training at Runtime After training, apply the learned improvements to your agent using `apply_training()`: ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonai.train.agents import apply_training from praisonaiagents import Agent agent = Agent(name="assistant", instructions="Be helpful") # Apply best iteration from a session apply_training(agent, session_id="train-abc123") # Now the agent uses learned improvements response = agent.start("Hello!") ``` ### Select Specific Iteration ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # Apply iteration #2 specifically (not just the best) apply_training(agent, session_id="train-abc123", iteration=2) ``` ### Inspect Before Applying ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonai.train.agents import get_training_profile # Preview the profile first profile = get_training_profile("train-abc123") print(f"Score: {profile.quality_score}/10") print(f"Suggestions: {profile.suggestions}") # Then apply if it looks good apply_training(agent, profile=profile) ``` ### Remove Training ```python theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} from praisonai.train.agents import remove_training # Remove training hook from agent remove_training(agent) ``` Training is applied via hooks - it doesn't modify the agent permanently. You can remove it anytime. *** ## CLI Commands ### Train Agents ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train agents [OPTIONS] [AGENT_FILE] ``` | Option | Description | Default | | -------------------- | ---------------------------- | ------------- | | `--input`, `-i` | Single input text | - | | `--expected`, `-e` | Expected output | - | | `--iterations`, `-n` | Number of iterations | `3` | | `--human`, `-h` | Use human feedback | `false` | | `--scenarios`, `-s` | Scenarios JSON file | - | | `--model`, `-m` | LLM for grading | `gpt-4o-mini` | | `--storage-backend` | `file`, `sqlite`, `redis://` | `file` | ### List Sessions ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train list ``` ### Show Session Details ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train show --iterations ``` The `--iterations` flag shows detailed suggestions for each iteration. ### Apply Training ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train apply [OPTIONS] ``` | Option | Description | Default | | ------------------- | -------------------------- | ------- | | `--iteration`, `-n` | Specific iteration number | best | | `--run`, `-r` | Run agent with this prompt | - | | `--agent`, `-a` | Path to agent YAML file | - | Example: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train apply train-abc123 --iteration 2 --run "Hello" ``` *** ## Grading Modes Automated grading using an LLM to evaluate responses: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train agents --input "Explain AI" --model gpt-4o ``` The LLM grades based on: * Relevance to input * Accuracy of information * Clarity and completeness * Match to expected output (if provided) Interactive mode where you score and provide feedback: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train agents --input "Write a haiku" --human ``` You'll be prompted to: 1. Review the agent's output 2. Provide a score (1-10) 3. Enter improvement suggestions *** ## Storage Backends Training data persists across sessions: ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} # File storage (default) praisonai train agents --input "Hello" --storage-backend file # SQLite (recommended for production) praisonai train agents --input "Hello" --storage-backend sqlite # Redis (distributed systems) praisonai train agents --input "Hello" --storage-backend redis://localhost:6379 ``` Training data is stored as JSON (not pickle), making it: * ✅ Human-readable * ✅ Git-friendly * ✅ Secure (no pickle vulnerabilities) * ✅ Cross-platform compatible *** ## Scenarios File For batch training, use a scenarios file: ```json theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} [ { "id": "greeting", "input_text": "Hello, how are you?", "expected_output": "A friendly response" }, { "id": "coding", "input_text": "Write a Python hello world", "expected_output": "print('Hello, World!')" } ] ``` ```bash theme={"theme":{"light":"vitesse-light","dark":"vitesse-dark"}} praisonai train agents --scenarios scenarios.json --iterations 5 ``` *** ## Learn vs Train | Aspect | Agent Learn | Agent Training | | ------------ | ------------------------------------ | ------------------------------ | | **Purpose** | Passive learning during interactions | Active iterative improvement | | **Trigger** | Automatic during `agent.start()` | Explicit CLI/SDK call | | **Feedback** | Implicit (patterns, insights) | Explicit (score, suggestions) | | **Storage** | Persona, insights, patterns stores | Scenarios, iterations, reports | | **Use Case** | Remember user preferences | Improve agent behavior | Agent Learn and Agent Training are **complementary**. Use Learn for continuous adaptation and Training for focused improvement sessions. See [Learn vs Train Comparison](/docs/concepts/learn-vs-train) for detailed differences. *** ## Related Passive continuous learning Detailed comparison